CodeScene for Openclaw

A comprehensive integration enabling AI agents to identify technical debt, hotspots, and team patterns through CodeScene.

membranedev
v1.0.4
Apr 30, 2026
0
617
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install codescene

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install codescene using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is CodeScene?

CodeScene is a powerful SaaS platform designed to visualize and manage the health of software architectures. By analyzing version control data, it identifies technical debt, code hotspots, and social patterns within development teams. This integration through Openclaw Skills allows your AI agent to programmatically access deep insights into code quality, risk, and team productivity.

By leveraging this skill, developers and managers can bridge the gap between raw code changes and high-level architectural health. The skill provides a structured way to interact with CodeScene data, ensuring that decisions are driven by historical code evolution and objective quality metrics rather than intuition alone.

CodeScene Use Cases

  • Automatically auditing technical debt and hotspots across multiple project repositories.
  • Integrating CodeScene delta analysis reports into automated Pull Request review workflows.
  • Mapping team knowledge distribution to identify single points of failure in complex codebases.
  • Programmatically managing projects, teams, and developer settings across an organization.
  • Monitoring code quality trends and triggering alerts when technical debt exceeds specific thresholds.

How CodeScene Works

  1. Install the Membrane CLI and authenticate your session to establish a secure link between your agent and the platform.
  2. Create or find a connection to your CodeScene instance, which handles the authentication handshake and token lifecycle automatically.
  3. Use natural language intent to search for available actions like listing projects or retrieving the latest analysis.
  4. Execute specific actions to fetch structured JSON data regarding files, authors, or architectural components.
  5. Optionally use the proxy request feature to send custom HTTP commands to the CodeScene API for specialized data requirements.

CodeScene Setup

Install the required CLI tool to begin using Openclaw Skills:

npm install -g @membranehq/cli@latest

Authenticate your agent environment:

membrane login --tenant --clientName=openclaw

Establish a connection to your CodeScene instance:

membrane connection ensure "https://codescene.com/" --json

CodeScene Data Schema & Taxonomy

The skill organizes CodeScene data into logical entities for easy retrieval:

Category Data Points
Projects Metadata, repository lists, and project-wide configurations.
Analyses Hotspots, knowledge maps, language breakdowns, and summary metrics.
Social Author lists, team structures, and contribution patterns.
Revisions File-level changes, commit summaries, and revision history.
Delta Analysis Focused analysis results for specific PRs or branches.

CodeScene Advanced Features

  • Direct API Proxying: Use membrane request to interact with any CodeScene endpoint not covered by pre-built actions.
  • Automated Auth Lifecycle: No need to manually manage API keys; Openclaw Skills handles credential refreshes and secure storage server-side.
  • Long-Polling Workflows: Utilize the --wait flag to monitor building connections or long-running analysis tasks.
  • Multi-Agent Optimization: Tooling adjustments specifically designed for integration with various AI agent harnesses.
  • Machine-Readable Output: Use the --json flag on any command for seamless programmatic data processing.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*